Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3023 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1958. Min Act: -0.0001

Data Index: 70433 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1759. Min Act: -0.0001

Data Index: 498815 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1747. Min Act: -0.0001

Data Index: 25729 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1747. Min Act: -0.0001

Data Index: 435832 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1468. Min Act: -0.0001

Data Index: 970672 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1468. Min Act: -0.0001

Data Index: 10783 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1124547 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1284222 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1369. Min Act: -0.0001

Data Index: 489529 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1348. Min Act: -0.0001

Data Index: 523566 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1337. Min Act: -0.0001

Data Index: 847886 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1041084 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1404. Min Act: -0.0001

Data Index: 301293 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1259. Min Act: -0.0001

Data Index: 305793 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1145078 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1294. Min Act: -0.0001

Data Index: 528288 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1286. Min Act: -0.0001

Data Index: 904113 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1270. Min Act: -0.0001

Data Index: 976853 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1214. Min Act: -0.0001

Data Index: 91652 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.1958. Min Range: -0.1958

Max Act: 0.1256. Min Act: -0.0001

Data Index: 906847 (C4 (Web Text))

Max Activating Token Index: 630